Discussion AMD Ryzen MegaThread! FAQ and Resources

[aldaia]

The 1800X is behind the i5-7600k. How could the 1600X trounce the i5 with 2 cores less?

Are you serious?
Your own post shows a 6 core eng sample at 3.3/3.7 GHz competing with i7s and clearly trouncing i5s.
1600X is 3.6/4.0 GHz !!!

If price is included in the equation, Rizen is truly amazing.

 

[truegenius]

is there any review of ryzen comparing performance in games of double and single rank memory ?
as i noticed that double rank gives more performance in games ( and winrar ) than single rank at same settings. ( though in phenom 1090t ).
( gta 5 showed 9% better performance for double rank than single at same settings ( there was no gpu bottleneck ) and speed. In comparision, cpu overclock of 12.5% gave just 4.5% performance increase despite game being cpu bottleneck ( single thread constanty above 95% and multi thread above 80%, gpu ( hd7950@1.3/1.575ghz core/memory clock respectively ) mostly between 50-60% ).

Btw, has anyone have any insight or idea if amd is laser cutting the die to make lower core sku or just using software, because to produce 4 core form 8 core die yields have to be abysmal which clearly won't happen, so if they don't laser cut then we can have core unlocking days back ( and probably one of the reason they didn't launched 4/6 core sku earlier )

 

[jdwii]

What about this graph folks:
(credit to AdoredTV)

Testing processors at low resolutions is not an indicator of future performance period

Hummm! A FX-8350 beating an i5-2500k in games? Well, I suppose that is possible if one cherry pick games and select only those that scale to 8 threads. Here we have the result of extensive gaming testing

FX-8370 is beated by i3s and Pentiums. There is no i5-2500k tested, but it seems evident that it will be not 50% slower than the i5-6600k

Nice article explaining why avoiding a GPU bottleneck is so important for testing and understanding CPU performance

http://www.techspot.com/news/68407-tackling-subject-gpu-bottlenecking-cpu-gaming-benchmarks-using.html

With the recent video going on twitter (official) with Lisa Su, it's very clear that the purpose is to hit with a "short blade" the market competitor and "nest in" that niche were "we are lower then 10 to 20% and most of the things we do it better plus there are a lot of tweaks to be done (RAM freq. wink wink)" ... so they make people choose to spend 100 to 500 dollars more to have a little 30 fps or other calculation 10\20 seconds (in a few cases) faster then Zen?

That is the point. Zen is not about being the best is about wounding the opponent (that is the effect it will come out, like the legionaries of roman empire sorry for the funny metaphor)... a massive product that will ask for a move in reponse by intel (OR MAYBE NOT!). And Intel or other competitor surely have a move in the sleeve.

Anyway, we are not considering also often the prices of the MOBO prices requested to build those intel based configs. so...really What we are talking about here?

Maybe Intell will move into Hyper miniaturization, all built in one Aio? is it called so? Total portability, will try to hit Amd or in general the market by moving the fight on the GFX or anyway graphic gaming territory.

The placement of the product just "below" Intel is clearly even for a donkey of marketing or business administration a clear killer ...

BTW thanks for deleting my posts.

Wrong if you are a pure gamer a 7700K cost about the same as the cheapest R7 CPU. Also a 7600K will OC to 4.5Ghz easy and beat the RX 1800X at 4.0Ghz in gaming while costing HALF as much

 

[jdwii]

Spoiler

Take a look, link is down again:
http://i.imgur.com/UTHepzS.png
Original link:
http://www.guru3d.com/news-story/amd-announces-ryzen-series-5-with-six-and-four-core-processors-available-april-11.html
(Returns 404)

Looks like Juan's guess on the clockspeeds is accurate.

The clocks and models were presented a long time ago. What's new there are the prices and release date: April 11

1600X ($249) -> competes against i5-7600k ($240), 6c/12t vs 4c/4t, 3.6/4.0 GHz vs 3.8/4.2 GHz

I think the 1600X will trounce the 7600k, especially when CCX/threading issues are dealt with.

1500X ($189) -> competes against i5-7500 ($190) and i3-7350k ($185). i3 has no chance, but i5 has very close clocks, without HT. Could be a close match.

My prediction of clocks was made much before any leak or official info...

The 1800X is behind the i5-7600k. How could the 1600X trounce the i5 with 2 cores less?

There is no 1400X. I guess you mean the 1500X. How the i3 "has no chance" when it is close to the 1700X with the double of cores?

Yes, I mean the 1500X, thanks

The i3 is close to the 1700X in unoptimized games. Everything else and the 1700X matches or beats Intel's quad cores. Life's not just games, you know. And would you buy a 4c/8t CPU that is good in almost anything, or a 2c/4t CPU that does only one thing well?

8150 did quite well in other things besides games to how did that work out for Amd's market share?

 

[-Fran-]

Wrong if you are a pure gamer a 7700K cost about the same as the cheapest R7 CPU. Also a 7600K will OC to 4.5Ghz easy and beat the RX 1800X at 4.0Ghz in gaming while costing HALF as much

Right back at you, jdwii. A pure gamer won't get the 1800X, but the 1700

A bit more expensive (than the i5), but way more justified price wise.

Until we don't see benchmarks for the rest of the line up, the best Ryzen CPU is the 1700 for any gamer.

Cheers!

EDT: Clarification of point.

 

[juanrga]

8C + GPU cores = Top of the line APU?

The top APU is 4 core Zen

 

[juanrga]

The 1800X is behind the i5-7600k. How could the 1600X trounce the i5 with 2 cores less?

Are you serious?
Your own post shows a 6 core eng sample at 3.3/3.7 GHz competing with i7s and clearly trouncing i5s.
1600X is 3.6/4.0 GHz !!!

If price is included in the equation, Rizen is truly amazing.

That graph was an early estimation made before launch and assuming the final chips would perform much better than they finally do in reviews. The commercial 6C RyZen has higher clocks than expected when that graph was made, but the IPC is lower than expected. The higher clocks are compensated by the lower IPC and thus the 1600X must be behind the i7-7700k in heavily multithreaded benches. Check the recentest estimation made by Anandtech for both multithread performance and single thread performance. The i7-7700k is above the 1600X in both, and the gap is higher if we consider games

Both Anandtech and AMD seem to consider the 1600X is the competition for the i5-7600k. The i5 will win in single thread and slightly threaded workloads and the R5 will win in heavily multithreaded workloads. I think that is why AMD uses the name "R5".

 

[thegentlewoman]

Ok, I like to be wrong, anyway my post above was besides too much wording perhaps referred to Sales (which is with finance- stategy - market product positioning) the most important thing in any thing you do today. (unfortunately) the position that goes between the Head and the shoulders, is the kill of honor, you don't feel nothing, you just die instantaneously. That is where the Johnny Top line hits.

At the moment also seeing the price and "somatizing" the whole revolution that is coming: Goddess competition Polemos, Athena Areia is here or should be raised as goddes, I feel like I am going to 1700ize my self. I'd have a cpu that will last 5+ wich is great.

One question I was wondering (especially reading last 10 pages) about and maybe we will just know in 1 year or more is what is the quality more going?
Where are AMD producers going to use the best quality of their materials, or how the "case" and fate will bring the batches of CPU to be best.
The first phase series not regarding if they are r7 r5 .. or the ones that will be produced late.

Maybe sombody will say that after all what is important is the SW, but maybe also material can be better (or this never actually verified in history).

So the question is to learn: better to buy early production (better quality indeed they are) or no, better wait when the products will start to be more then the demand, then quality will be better ?
or this is just a legend?

Maybe with tech items all is just random, you can get a failing item and variables are too many, dusty, humidity, AC\DC levels and stuff like that, interaction, human factor, compatibility that we can't say after all...?

I am just thinking how much prices after all have gone down.
With Dell (OK leave the 200 EURO over price out)
I spent around 1200 Euro (?) for a pentium 4 It was a DELL dimension slim build in 2004 end, it last maybe 2\3 years then it started to take hits. It never had a serious videocard, the vga also is integrated, ram 2 to 4 dimm ... today we have promises to reach 5+ years and this stuff LOOKs to be going to last so as they say\we say.

I spend 1100 for a super quality (lowest of top gamma) and I can do a lot of stuff.

My built, just imaginery:

PSU Corsair RM x 750W 105
Cpu 1700 Johnny Ryzen 349
Corsair veng cl 14 3200 16 gb 170 (or waiting for 3200 Flare X - Fortis strips - seems crucial stuff here folks... I don't think it's just marketing)
Father Board (darth) - x370 Prime Asus Pro 160
Xfx Rx 480 8 gb - 215
SSD 275 gb(linux and win?) -Crucial MX 90
1 tb EZEX WD blue 7200 50
----------------
Gonna get head set Logitech g430 (for it versatility) 51
A nice seat (?) 200
Trakir 5 250+
AverMedia c985? 150+
An external drive 3 tb 100

What I wanna say is that we spend the same or less and we have totally stronger (or simply better) machines then yesterday. Ok I know that these are laws written years ago and these rules are actually obsolete I also read but... some people say it's a great time to make a configuration. is this true?
What do you think about this?

I think that retailers in general are going to be happy for what is going to happen.
Just think about all the people that can't afford (I can't) and will buy from India to China to Russia to Europe Africa Americas' Australia especially the most populated ones I mentioned. Imagine how much is crucial how much these HW consumes. (AMD really is democratizing participation to tech ..maybe this is not clear? or am I wrong?) and how much minerals and also especially energy more will be consumed in next years (more then before?) ... We are approaching the next kardashev scale (maybe also these "laws" are outdated ...) I believe that less energy we consume the better we are anyway.

Vega 10 and 11 ... same house -... aren't going to relatively do better but consume less or they will always ask for 750 600 W monsters ?
I am really really curious about this and also about NAVI 2018. I am sure some of you already know the answer on this.
-------------
Looking at the graphics above. It's clear that "THE BEST BUY" is a 1600 X and then u put on it a Vent like Noctua or Cryorig (as someone suggested me this brand is good too) and you will have a fighter for Intel... anyway. Single tread isn't going to be "abandoned"?
as with our SW we will do much bigger, things with bigger datas, bigger multitasking.

Just the VR Leap motion thing comes to my mind...

 

[jdwii]

Wrong if you are a pure gamer a 7700K cost about the same as the cheapest R7 CPU. Also a 7600K will OC to 4.5Ghz easy and beat the RX 1800X at 4.0Ghz in gaming while costing HALF as much

Right back at you, jdwii. A pure gamer won't get the 1800X, but the 1700

A bit more expensive (than the i5), but way more justified price wise.

Until we don't see benchmarks for the rest of the line up, the best Ryzen CPU is the 1700 for any gamer.

Cheers!

EDT: Clarification of point.

So a gamer should pay the same and get less? Is this Amd's new message i remember when Amd processors used to offer more FPS for less money.

Ryzen seems good for everything else but for people who just game and use their PC's for normal tasks i can't see a reason why they would need a CPU that performs worse in games but works good in blender.

 

[thegentlewoman]

The differences are so slight... really unless we do gamin'competition (professional ones) it is clearly a tete a tete. It's just a philosophical choice now, a choice of "a flag"... and anyway for mutlithread and streaming ryzen is said to be better (so since most of ppl, the "selfie generation" all these youtube channelers and stuff do it... I think ryzen is gonna take it all).. just pro (gamers) are going to stick on Intel.
Let the voice spread, from Archaeology to Zombies all the people will move to Ryzen because they know they have a tractor engine to do all their rendering stuff for a good price. I mean this is obvious. It would be nice now to learn what is Intel going to do (we know AMD strategy we don't know Intel's do we?) beside lowering its price and bs like that.

 

[-Fran-]

Wrong if you are a pure gamer a 7700K cost about the same as the cheapest R7 CPU. Also a 7600K will OC to 4.5Ghz easy and beat the RX 1800X at 4.0Ghz in gaming while costing HALF as much

Right back at you, jdwii. A pure gamer won't get the 1800X, but the 1700

A bit more expensive (than the i5), but way more justified price wise.

Until we don't see benchmarks for the rest of the line up, the best Ryzen CPU is the 1700 for any gamer.

Cheers!

EDT: Clarification of point.

So a gamer should pay the same and get less? Is this Amd's new message i remember when Amd processors used to offer more FPS for less money.

Ryzen seems good for everything else but for people who just game and use their PC's for normal tasks i can't see a reason why they would need a CPU that performs worse in games but works good in blender.

Not necessarily, jdwii. I got the i7 because I knew going forward it would justify the extra price and I was right.

At stock clocks, the i5 and i7 are pretty much the same (gaming wise) and the i7 puts the premium in it's HT capabilities, right? Both OC about the same (on average) and behave closely in games, but nowadays the i7 is the better purchase IMO (yes, for games). That is why I think is not that idiotic to suggest a person to go with an 8C/16T CPU instead of a 4C/4T CPU just because it's better when they are kind of close in price. I think that is the main reason AMD put the 1700 right next to the i7 (non -E, that is), because the 4C CPUs are starting to take the place of 2C CPUs for games.

Depending on the performance of the 1400 and 1500X CPUs, they might be the new value kings for games.

Cheers!

 

[lilcinw]

Phoronix has a review of Ryzen core scaling: http://www.phoronix.com/scan.php?page=article&item=amd-ryzen-cores&num=1

 

[Eximo]

8C + GPU cores = Top of the line APU?

The top APU is 4 core Zen

Sorry, I was thinking 4C/8T from one CCX + the GPU, which is what it is.

 

[-Fran-]

Phoronix has a review of Ryzen core scaling: http://www.phoronix.com/scan.php?page=article&item=amd-ryzen-cores&num=1

That's really interesting to see. I wonder if the extra L3 for the 2+2 is helping it off-set some of the load in the games when fully stressed out.

Cheers!

 

[salgado18]

Phoronix has a review of Ryzen core scaling: http://www.phoronix.com/scan.php?page=article&item=amd-ryzen-cores&num=1

The most interesting part I think is this: scaling is off, it's a bad benchmark, but every situation in which there is only one CCX active, performance is a lot better than with two CCX. Makes me sad for the 4-cores with 2+2

But also very hopeful for the APUs

 

[aldaia]

Check the recentest estimation made by Anandtech for both multithread performance and single thread performance. The i7-7700k is above the 1600X in both, and the gap is higher if we consider games

I compile and run simulations that scale almost linearly with cores, so I only care about MT. What I see in that (MT) estimation is that 1600X offers i7 performance for i5 price. Knowing what I run I bet that 1600X will provide significantly more performance that i7, but that is my particular case. I also game, but I'm usually bottle-necked by the GPU. Regarding ST, if ST is all you run. then don't buy i5 or i7 they are a waste of money, an i3 is all you need.

 

[jaymc]

Spoiler

What about this graph folks:
(credit to AdoredTV)

Testing processors at low resolutions is not an indicator of future performance period

Nice article explaining why avoiding a GPU bottleneck is so important for testing and understanding CPU performance

http://www.techspot.com/news/68407-tackling-subject-gpu-bottlenecking-cpu-gaming-benchmarks-using.html

There is a huge issue with the 'low resolution / settings' approach though- and that is that many of the higher graphics settings also impact cpu (quite a few effects load the CPU for example, whilst higher draw distance increases the number of AI / physics objects on screen).

I think what people keep missing over and over is exactly what a low resolution / settings 'cpu' gaming test actually shows- it shows 1 specific facet of performance: CPU bound *draw call* performance. It imo however ignores many other sources of CPU load, meaning a high clocked low core count CPU has an unrealistic advantage. There are a few cases where Ryzen bests Intel at higher resolution but not at 1080p lowered settings- the reason being all those extra threads / cache can be put to use when you load everything up. I mean these 'cpu' tests regularly show the i5 matching the i7 in games- yet when you get into a multiplayer scenario the i5 really starts to struggle (whereas Ryzen or an i7 show real value). These cpu game tests are an interesting data point- but I think far too much emphasis is put on them. I'd like to see more high load multi player tests (a number of vids on YouTube suggest an R7 is a much better processor than an i5 for example in such cases- as the workload isn't a flat out fps race).

The final point is that there are a few cases where Ryzen isn't performing anywhere near where it should (AOTS for example)- and based on early comments from the developers that is something that is likely to change. My guess is AOTS post patch will put the R7 parts above the 7700k but probably below the 6900k.

That's a nice point. Why don't MP game developers make a benchmark option, in which they start a match with only pre-programmed bots and camera movement? That wouldn't be hard to make, I think.

But about low-res testing, if they test at maximum settings on 1080p, we must agree that all possible CPU settings are on, so as long as the GPU is powerful enough, there's no problem.

Spoiler

I said it first, the problem is not the scheduler... and AMD now officially admits the W10 scheduler is working fine for RyZen

https://community.amd.com/community/gaming/blog/2017/03/13/amd-ryzen-community-update?sf62107357=1

Funny evidence says otherwise though... Still, if AMD says so, then that's the end of it?

LOL, no it isn't. Even AMD engies can be wrong about stuff like that.

I still see The Stilt being serious about it:

"I did some 3D testing and eventhou there is not nearly enough data to confirm it, I'd say the SMT regression is infact a Windows 10 related issue.
In 3D testing I did recently on Windows 10, the title which illustrated the biggest SMT regression was Total War: Warhammer."

https://forums.anandtech.com/threads/ryzen-strictly-technical.2500572/page-8

Well, I guess it's old by now, but there hasn't been any patches for TW:W that I know of to address that performance delta.

EDIT: I'd put some links to a French review/article investigating a bit more about core distribution (AKA core parking) and cache movement, but it seems it's taboo to do it or Toms thinks people has issues with google translate.

But long story short: heavy context switches hurt Ryzen badly. That is an scheduler problem. Whether AMD wants to admit/pass blame on that or not, is something else.

Cheers!

If there's nothing wrong with how Win10 handles Ryzen why did Microsoft say they were releasing an update for it in their batch Windows Updates due for release in April ?

Maybe because it works, but could work better. Like the power profile thing, AMD said they are fixing but Microsoft owns the system, so a fix on their side will help too. Also, I believe they said "nothing is wrong with how W10 handles threads for Ryzen", but not other things.

I don't believe that, there's definitely something wrong with how treads are being handled, especially in certain games (weather it's windows or the game engine at fault or both even).
You can see that much on the games that are having trouble on youtube reviews with single cores maxing out an other cores idling.
Weather this get's fixed with windows update or game patch's remains to be seen. But there is definitely something going wrong with tread allocation in games that's not happening on Intel chips.

Also saying that fixing the outlying games that are worst affected is only gonna raise the average gaming performance by 1-2 percent is just a silly statement..
So what, Who cares how much it raises the average for gods sake...
If it wasn't for those games that are worst affected (dropping 20/30 frames an the like) no one would be complaining at all...!!

Otherwise Ryzen performs great.

I did state before the chip came out that there would be problems with the first wave of boards etc.. this is new technology there is always problems with the first version of anything... maybe it was rushed.. maybe if it was late there would of been hell to pay too...
I can't wait for game patches to start coming out and new BIOS's an windows updates also...

When this problem with the games gets sorted will people finally just admit Ryzen is a great chip i wonder ? Or will some people just start looking for something else to complain about... I certainly hope not anyway.
I'm sure all new titles will be optimized and a lot of whats already out... Maybe not some of the older games though unfortunately.

I still believe the chip is an Excellent CPU.. It's a pity about all this fiasco taking away from it that's for sure.
Especially seen as how the drop in frame rates in the games affected is imperceivable.

 

[jdwii]

Wrong if you are a pure gamer a 7700K cost about the same as the cheapest R7 CPU. Also a 7600K will OC to 4.5Ghz easy and beat the RX 1800X at 4.0Ghz in gaming while costing HALF as much

Right back at you, jdwii. A pure gamer won't get the 1800X, but the 1700

A bit more expensive (than the i5), but way more justified price wise.

Until we don't see benchmarks for the rest of the line up, the best Ryzen CPU is the 1700 for any gamer.

Cheers!

EDT: Clarification of point.

So a gamer should pay the same and get less? Is this Amd's new message i remember when Amd processors used to offer more FPS for less money.

Ryzen seems good for everything else but for people who just game and use their PC's for normal tasks i can't see a reason why they would need a CPU that performs worse in games but works good in blender.

Not necessarily, jdwii. I got the i7 because I knew going forward it would justify the extra price and I was right.

At stock clocks, the i5 and i7 are pretty much the same (gaming wise) and the i7 puts the premium in it's HT capabilities, right? Both OC about the same (on average) and behave closely in games, but nowadays the i7 is the better purchase IMO (yes, for games). That is why I think is not that idiotic to suggest a person to go with an 8C/16T CPU instead of a 4C/4T CPU just because it's better when they are kind of close in price. I think that is the main reason AMD put the 1700 right next to the i7 (non -E, that is), because the 4C CPUs are starting to take the place of 2C CPUs for games.

Depending on the performance of the 1400 and 1500X CPUs, they might be the new value kings for games.

Cheers!

I agree with that If Ryzen was actually outperforming the 7700K in the same games the 6900K is.

That's the point even when games scale to 8 cores Ryzen can't beat a 7700K and can't even consistently beat a 230$ I5.

Least pricing on the R5 seems to be really great now we wait on performance numbers. I really thought Ryzen might need a patch or something since it seems like its performing similar in 4 and 8 core configurations in games that can easily use 8 cores.

 

[jdwii]

Check the recentest estimation made by Anandtech for both multithread performance and single thread performance. The i7-7700k is above the 1600X in both, and the gap is higher if we consider games

I compile and run simulations that scale almost linearly with cores, so I only care about MT. What I see in that (MT) estimation is that 1600X offers i7 performance for i5 price. Knowing what I run I bet that 1600X will provide significantly more performance that i7, but that is my particular case. I also game, but I'm usually bottle-necked by the GPU. Regarding ST, if ST is all you run. then don't buy i5 or i7 they are a waste of money, an i3 is all you need.

Least Amd employee's aren't downplaying single core performance like that anymore. I remember when someone from Amd was doing that months before launch even once told me we already have high speed single core CPUs go with that if you care about single core performance.

See the thing that's wrong with that statement is Intel isn't selling me 1 core compared to lets say 6 from Amd they are selling me 4 cores and Amd would be selling 6. If games use one core at higher usage compared to the other 5 cores then we might have a issue with the game not getting the same numbers compared to a faster per core processor. Most games are starting to finally use 4 cores at least. Anything over a 1060/480 would bottleneck a I3 and you won't be getting the full usage out of your GPU

I think something is wrong with the way Ryzen actually works 4+4 cores so when games scale beyond 4 cores it doesn't act correctly, I have no idea why

I read this at Jayztwocents youtube comment and basically laughed at how badly some people are
"Also, why didn't you at least test the non-demanding games at higher resolutions to flesh out the differences (or more precisely the clear Ryzen lead). Like, seriously are you trying to make the i7 look as good as possible?"

 

[truegenius]

You can see that much on the games that are having trouble on youtube reviews with single cores maxing out an other cores idling.

Thats because core part of cpu can bottleneck by 2 ways, single core thourghput and multi core throughput.
And here ryzen is showing single core throughput limit and it is getting amplified by uncore part ( that is poor memory latency) ( i am surprized how ryzen even manage to get 99% of theoritical ram bandwidth while having latency of ddr1 era ).
And this is why people care about ipc or atleast single core throughput ( ipc*clock speed ) by better single core performance they don't actually mean that they want a single or dual core only cpu.

 

[aldaia]

See the thing that's wrong with that statement is Intel isn't selling me 1 core compared to lets say 6 from Amd they are selling me 4 cores and Amd would be selling 6. If games use one core at higher usage compared to the other 5 cores then we might have a issue with the game not getting the same numbers compared to a faster per core processor. Most games are starting to finally use 4 cores at least. Anything over a 1060/480 would bottleneck a I3 and you won't be getting the full usage out of your GPU

I don't get why some people in this thread are trying to convince me that something more expensive and with less performance (for my needs) is better, My top priority is not gaming, gaming is secondary, i never spend more than $150-180 on a GPU, any CPU is good enough to get full usage of that. On the other hand I compile a lot, and that is an area where Ryzen shines. I also run simulations that in all aspects are perfectly parallel with zero data communication. I can even spawn the exact number of threads and fix them to specific CPUs to avoid thread migration (simulations run for several days). So my expectations are to do at least as good as MT Cinebench if not better. Why the hell should I buy an i7 7700K for $350 when a $250 R5 1600X will give me more performance where it matters and exactly the same while gaming? And if I can spare $350, what I should buy is R7 1700.

 

[gamerk316]

You can see that much on the games that are having trouble on youtube reviews with single cores maxing out an other cores idling.

Thats because core part of cpu can bottleneck by 2 ways, single core thourghput and multi core throughput.
And here ryzen is showing single core throughput limit and it is getting amplified by uncore part ( that is poor memory latency) ( i am surprized how ryzen even manage to get 99% of theoritical ram bandwidth while having latency of ddr1 era ).
And this is why people care about ipc or atleast single core throughput ( ipc*clock speed ) by better single core performance they don't actually mean that they want a single or dual core only cpu.

Pretty much this.

As of noted for YEARS now: Games really do not scale beyond a handful of CPU cores in any meaningful way, due largely to the GPU rendering process being single-thread dominated. New Low-Level APIs help this somewhat, but you still have two/three threads dominating the total workload.

Essentially, games are a classic case of Amdahl Law:

https://en.wikipedia.org/wiki/Amdahl%27s_law

Essentially, your maximum theoretical speedup of making a program more parallel is limited by the part of the program that is serial. Or simply put, if 60% of the program can not be made parallel, then your maximum speedup you can obtain via threading alone is capped at 40%.

Point being, there's nothing wrong with how Windows handles threading; if you have three threads doing 90% of the total workload, you're going to see a lot of cores idle on a 16 core CPU. Simple as that.

 

[gamerk316]

Least Amd employee's aren't downplaying single core performance like that anymore. I remember when someone from Amd was doing that months before launch even once told me we already have high speed single core CPUs go with that if you care about single core performance.

JF_AMD. His hyping of BD really hurt AMD badly once we found out it wasn't anywhere closed to what he was claiming.

 

[jdwii]

See the thing that's wrong with that statement is Intel isn't selling me 1 core compared to lets say 6 from Amd they are selling me 4 cores and Amd would be selling 6. If games use one core at higher usage compared to the other 5 cores then we might have a issue with the game not getting the same numbers compared to a faster per core processor. Most games are starting to finally use 4 cores at least. Anything over a 1060/480 would bottleneck a I3 and you won't be getting the full usage out of your GPU

I don't get why some people in this thread are trying to convince me that something more expensive and with less performance (for my needs) is better, My top priority is not gaming, gaming is secondary, i never spend more than $150-180 on a GPU, any CPU is good enough to get full usage of that. On the other hand I compile a lot, and that is an area where Ryzen shines. I also run simulations that in all aspects are perfectly parallel with zero data communication. I can even spawn the exact number of threads and fix them to specific CPUs to avoid thread migration (simulations run for several days). So my expectations are to do at least as good as MT Cinebench if not better. Why the hell should I buy an i7 7700K for $350 when a $250 R5 1600X will give me more performance where it matters and exactly the same while gaming? And if I can spare $350, what I should buy is R7 1700.

No one is trying to convince you i said several times that Ryzen is superior to Intel in everything but gaming for the money.

In your case Ryzen is amazing in almost all cases but gaming Ryzen is at least not bad. Once i get more $$$ a 1700 is becoming my rig that handles my handbrake machine and some other tasks.

If you are doing work like you said i'd never recommend a I5 over a 6 core Ryzen part, if anything i'd try and tell you to get a 1700 at least for your work try and fit it in the budget

Lame fact about me, i'm having more fun from BOTW on my switch then i have been on my PC for 2 years. Power is not everything(also why i'm not as active on the forums).

 

[juanrga]

Phoronix has a review of Ryzen core scaling: http://www.phoronix.com/scan.php?page=article&item=amd-ryzen-cores&num=1

The most interesting part I think is this: scaling is off, it's a bad benchmark, but every situation in which there is only one CCX active, performance is a lot better than with two CCX. Makes me sad for the 4-cores with 2+2

But also very hopeful for the APUs

That bench is weird. 3+0 faster than 4+0? 1+1 faster than 2+2? I wonder 0+0 must be a real winner here

Don't have too much hope on the APUs. Yes, they have a full CCX, but they use a different CCX with half the L3 cache than its big brothers. Half the cache will hurt performance in games.